Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Classification Algorithms”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6Linked to original sources
PubMed2004

Development of the cubic least squares mapping linear-kernel support vector machine classifier for improving the characterization of breast lesions on ultrasound.

An efficient classification algorithm is proposed for characterizing breast lesions. The algorithm is based on the cubic least squares mapping and the linear-kernel support vector machine (SVM(LSM)) classifier. Ultrasound images of 154 confirmed lesions (59 benign and 52 malignant solid masses, 7 simple cysts, and 32 complicated cysts) were manually segmented by a physician using a custom developed software. Texture and outline features and the SVM(LSM) algorithm were used to design a hierarchical tree classification system. Classification accuracy was 98.7%, misdiagnosing 1 malignant an 1 benign solid lesions only. This system may be used as a second opinion tool to the radiologists.

Breast Diseases↗
PubMed2003

[The Narcotrend monitor. Development and interpretation algorithms].

The Narcotrend performs an automatic interpretation of the electroencephalogram (EEG) during anaesthesia. The classification algorithms have been developed on the basis of visually classified EEG epochs. The classification scheme which was used for these visual assessments has its origin in sleep analysis and was adapted for the EEG during anaesthesia. From the awake state to very deep anaesthesia, 15 stages (A, B(0-2), C(0-2), D(0-2), E(0-2), F(0-1)) are distinguished. The transformation of these stages into a numerical scale from 100 to 0 is a further refinement for a differentiated presentation of EEG effects. For the automatic classification multivariate discriminant functions are used. Age-related changes of the EEG were incorporated. The device contains functions for the identification of artifacts. The EEG can be recorded from a frontal channel using standard ECG electrodes, other electrode positions and types can be chosen. The device has been clinically and scientifically validated.

Algorithms↗
PubMed2000

Medical text representations for inductive learning.

Inductive learning algorithms have been proposed as methods for classifying medical text reports. Many of these proposed techniques differ in the way the text is represented for use by the learning algorithms. Slight differences can occur between representations that may be chosen arbitrarily, but such differences can significantly affect classification algorithm performance. We examined 8 different data representation techniques used for medical text, and evaluated their use with standard machine learning algorithms. We measured the loss of classification-relevant information due to each representation. Representations that captured status information explicitly resulted in significantly better performance. Algorithm performance was dependent on subtle differences in data representation.

Algorithms↗
PubMed2004

A web portal for classification of expression data using maximal margin linear programming.

The Maximal Margin (MAMA) linear programming classification algorithm has recently been proposed and tested for cancer classification based on expression data. It demonstrated sound performance on publicly available expression datasets. We developed a web interface to allow potential users easy access to the MAMA classification tool. Basic and advanced options provide flexibility in exploitation. The input data format is the same as that used in most publicly available datasets. This makes the web resource particularly convenient for non-expert machine learning users working in the field of expression data analysis.

Algorithms↗
PubMed2001

Using Bayesian networks in the construction of a bi-level multi-classifier. A case study using intensive care unit patients data.

Combining the predictions of a set of classifiers has shown to be an effective way to create composite classifiers that are more accurate than any of the component classifiers. There are many methods for combining the predictions given by component classifiers. We introduce a new method that combine a number of component classifiers using a Bayesian network as a classifier system given the component classifiers predictions. Component classifiers are standard machine learning classification algorithms, and the Bayesian network structure is learned using a genetic algorithm that searches for the structure that maximises the classification accuracy given the predictions of the component classifiers. Experimental results have been obtained on a datafile of cases containing information about ICU patients at Canary Islands University Hospital. The accuracy obtained using the presented new approach statistically improve those obtained using standard machine learning methods.

Algorithms↗
PubMed2002

Feature selection for the classification of movements from single movement-related potentials.

Classification of movement-related potentials recorded from the scalp to their corresponding limb is a crucial task in brain-computer interfaces based on such potentials. Many features can be extracted from raw electroencephalographic signals to be used for classification, but the utilization of irrelevant or superfluous features is detrimental to the performance of classification algorithms. It is, therefore, necessary to select a small number of relevant features for the classification task. This paper demonstrates the use of two feature selection methods to choose a small number (10-20) of relevant features from a bank containing upward of 1000 features. One method is based on information theory and the other on the use of genetic algorithms. We show that the former is poorly suited for the aforementioned classification task and discuss the probable reasons for this. However, using a genetic algorithm on data recorded from five subjects we demonstrate that it is possible to differentiate between the movements of two limbs with a classification accuracy of 87% using as little as 10 features without subject training. With the addition of a simple coding scheme, this method can be applied to multiple limb classification and a 63% classification accuracy rate can be reached when attempting to distinguish between three limbs.

Adult↗
PubMed2006

Ordering and finding the best of K > 2 supervised learning algorithms.

Given a data set and a number of supervised learning algorithms, we would like to find the algorithm with the smallest expected error. Existing pairwise tests allow a comparison of two algorithms only; range tests and ANOVA check whether multiple algorithms have the same expected error and cannot be used for finding the smallest. We propose a methodology, the MultiTest algorithm, whereby we order supervised learning algorithms taking into account 1) the result of pairwise statistical tests on expected error (what the data tells us), and 2) our prior preferences, e.g., due to complexity. We define the problem in graph-theoretic terms and propose an algorithm to find the "best" learning algorithm in terms of these two criteria, or in the more general case, order learning algorithms in terms of their "goodness." Simulation results using five classification algorithms on 30 data sets indicate the utility of the method. Our proposed method can be generalized to regression and other loss functions by using a suitable pairwise test.

Algorithms↗
PubMed2000

Content-based retrieval in picture archiving and communication systems.

A COntent-Based Retrieval Architecture (COBRA) for picture archiving and communication systems (PACS) is introduced. COBRA improves the diagnosis, research, and training capabilities of PACS systems by adding retrieval by content features to those systems. COBRA is an open architecture based on widely used health care and technology standards. In addition to regular PACS components, COBRA includes additional components to handle representation, storage, and content-based similarity retrieval. Within COBRA, an anatomy classification algorithm is introduced to automatically classify PACS studies based on their anatomy. Such a classification allows the use of different segmentation and image-processing algorithms for different anatomies. COBRA uses primitive retrieval criteria such as color, texture, shape, and more complex criteria including object-based spatial relations and regions of interest. A prototype content-based retrieval system for MR brain images was developed to illustrate the concepts introduced in COBRA.

Humans↗
PubMed2003

MBGD: microbial genome database for comparative analysis.

MBGD is a workbench system for comparative analysis of completely sequenced microbial genomes. The central function of MBGD is to create an orthologous gene classification table using precomputed all-against-all similarity relationships among genes in multiple genomes. In MBGD, an automated classification algorithm has been implemented so that users can create their own classification table by specifying a set of organisms and parameters. This feature is especially useful when the user's interest is focused on some taxonomically related organisms. The created classification table is stored into the database and can be explored combining with the data of individual genomes as well as similarity relationships among genomes. Using these data, users can carry out comparative analyses from various points of view, such as phylogenetic pattern analysis, gene order comparison and detailed gene structure comparison. MBGD is accessible at http://mbgd.genome.ad.jp/.

Algorithms↗
PubMed2004

Tree analysis of mass spectral urine profiles discriminates transitional cell carcinoma of the bladder from noncancer patient.

BACKGROUND: Recent advances in proteomic profiling technologies, such as surface-enhanced laser desorption/ionization mass spectrometry (SELDI), have allowed preliminary profiling and identification of tumor markers in biological fluids in several cancer types and establishment of clinically useful diagnostic computational models. We developed a bioinformatics tool and used it to identify proteomic patterns in urine that distinguish transitional cell carcinoma (TCC) from noncancer. METHODS: Proteomic spectra were generated by mass spectroscopy (surface-enhanced laser desorption and ionization). A preliminary "training" set of spectra derived from analysis of urine from 46 TCC patients, 32 patients with benign urogenital diseases (BUD), and 40 age-matched unaffected healthy men were used to train and develop a decision tree classification algorithm that identified a fine-protein mass pattern that discriminated cancer from noncancer effectively. A blinded test set, including 38 new cases, was used to determine the sensitivity and specificity of the classification system. RESULTS: The algorithm identified a cluster pattern that, in the training set, segregated cancer from noncancer with sensitivity of 84.8% and specificity of 91.7%. The discriminatory pattern correctly identified. A sensitivity of 93.3% and a specificity of 87.0% for the blinded test were obtained when comparing the TCC vs. noncancer. CONCLUSIONS: These findings justify a prospective population-based assessment of proteomic pattern technology as a screening tool for bladder cancer in high-risk and general populations.

Adult↗
PubMed1998

Learning differential diagnosis of erythemato-squamous diseases using voting feature intervals.

A new classification algorithm, called VFI5 (for Voting Feature Intervals), is developed and applied to problem of differential diagnosis of erythemato-squamous diseases. The domain contains records of patients with known diagnosis. Given a training set of such records, the VFI5 classifier learns how to differentiate a new case in the domain. VFI5 represents a concept in the form of feature intervals on each feature dimension separately. classification in the VFI5 algorithm is based on a real-valued voting. Each feature equally participates in the voting process and the class that receives the maximum amount of votes is declared to be the predicted class. The performance of the VFI5 classifier is evaluated empirically in terms of classification accuracy and running time.

Algorithms↗
PubMed1996

Reliable computer-assisted classification of the EEG: EEG variants in index cases and their first degree relatives.

A method which optimizes on global properties of sample recordings is proposed for the definition of and the discrimination between electroencephalogram (EEG) classes. The sample was drawn from students at the University of Heidelberg from 1974 to 1978 and consists of 15 healthy index cases clinically ascertained as belonging to the low voltage EEG group. In addition, the three clinically defined groups: diffuse beta (18 index cases), borderline alpha (12 index cases) and monomorphous alpha (18 index cases) have been included in the study, as well as the first degree relatives of the index cases, thus providing a clinical classification into four groups. The proposed method provides an automatic and reliable classification algorithm using discriminant and cluster analysis. The relation between such an automatized classification and clinical classification schemes is investigated. In particular, the inheritance of the low voltage EEG, the question on sex differences and the question of a simple Mendelian mechanism had been examined. The method of random splittings had been applied for discriminant and cluster analysis. Our findings can be summarized as follows: (1) except for the monomorphous alpha EEG group, the clinical classification shows rather marginal separation (discriminating performance 60% to 75%), while a new and more reliable grouping scheme improves the discriminating performance up to 87% to 91%. The latter scheme leads to the concept of personal channel pattern (PCP) and was compared to the clinical classification scheme by means of contingency tables; (2) only a weak correlation between the clinically and PCP-based groups could be found (Cramér Index: 0.27). Accordingly, we continued to investigate the extent to which the proposed EEG classification scheme can nevertheless explain the genetic mechanisms apparently involved in the low voltage EEG. We thus considered the role of sex differences manifest in our proposed new grouping scheme; (3) males occurred more frequently in the new group 3 and females more frequently in the new group 1. In this regard, a much better correlation of the new groups between mothers and children than between fathers and children was observed; and (4) with help of our new PCP scheme, we have been able to reproduce a simple two gene Mendelian scheme to explain inheritance of the clinical low voltage EEG group. In this PCP-based scheme, the low voltage property does not occur when dominance of a certain gene (called gene A) is absent.

Adult↗
PubMed1994

Brain segmentation and white matter lesion detection in MR images.

This paper presents a review of methods and techniques that have been proposed for the segmentation of magnetic resonance (MR) images of the brain, with a special emphasis on the segmentation of white matter lesions. First, artifacts affecting MR images (noise, partial volume effect, and shading artifact) are reviewed and methods that have been proposed to correct for these artifacts are discussed. Next, a taxonomy of generic segmentation algorithms is presented, categorized as region-based, edge-based, and classification algorithms. For each category, the applications proposed in the literature are subdivided into 2-D, 3-D, or multimodal approaches. In each case, tables listing authors, bibliographic references, and methods used have been compiled and are presented. This description of segmentation algorithms is followed by a section on techniques proposed specifically for the analysis of white matter lesions. Finally, a section is dedicated to a review and a comparison of validation methods proposed to assess the accuracy and the reliability of the results obtained with various segmentation algorithms.

Algorithms↗
PubMed2003

Analyzing the subcortical dementia syndrome of Parkinson's disease using the RBANS.

On mental status examinations, groups of equally impaired patients with subcortical (Huntington's disease, HD; Parkinson's disease, PD) or cortical (Alzheimer's disease, AD) dementias exhibit different patterns of neuropsychological deficits. Using the Repeatable Battery for Assessment of Neuropsychological Status (RBANS), classification accuracies of 90% or greater have been reported for individual patients with AD or HD. To test the generality of the RBANS classification algorithm, we studied patients with dementia (AD and PDD) and without dementia (PDND). Classification accuracies were AD: 87%, PDD: 78%, and PDND: 39%. Comparisons of performance on subtests of the RBANS showed that all groups performed more poorly on tests that require motor skill or rapid information processing and that memory performance by the PD groups was not improved by procedures that enhance encoding and facilitate retrieval. The RBANS is useful for discriminating patterns of cognitive impairment in PD and AD, but only if the diagnosis of dementia is established independent of the RBANS test results. Cognitive slowing is not specific to subcortical dementia and current concepts of memory dysfunction in PD may require re-examination.

Aged↗
PubMed2004

Automated morphometric analysis of the cat retinal alpha/Y, beta/X and delta ganglion cells using wavelet statistical moment and clustering algorithms.

Computational morphological analysis comprises the development of measures (indicators) that describe different form attributes of a neuron and provides additional parameters for classification algorithms. Our work addressed the problem of small group sizes often encountered in neuromorphological and neurophysiological research, automated classification tasks (unsupervised learning) and introduced a new morphological measure: the wavelet statistical moment. We analysed cat alpha/Y, beta/X and delta Golgi-stained retinal ganglion cells using six different shape features (circularity, 2(nd) statistical moment and entropy of Gaussian blurred images, wavelet statistical moment, number of terminations and the fractal dimension). This allowed us to compare the sensitivity of the methods in uniquely describing morphological attributes of these cells.

Algorithms↗
PubMed2006

Improving computational predictions of cis-regulatory binding sites.

The location of cis-regulatory binding sites determine the connectivity of genetic regulatory networks and therefore constitute a natural focal point for research into the many biological systems controlled by such regulatory networks. Accurate computational prediction of these binding sites would facilitate research into a multitude of key areas, including embryonic development, evolution, pharmacogenemics, cancer and many other transcriptional diseases, and is likely to be an important precursor for the reverse engineering of genome wide, genetic regulatory networks. Many algorithmic strategies have been developed for the computational prediction of cis-regulatory binding sites but currently all approaches are prone to high rates of false positive predictions, and many are highly dependent on additional information, limiting their usefulness as research tools. In this paper we present an approach for improving the accuracy of a selection of established prediction algorithms. Firstly, it is shown that species specific optimization of algorithmic parameters can, in some cases, significantly improve the accuracy of algorithmic predictions. Secondly, it is demonstrated that the use of non-linear classification algorithms to integrate predictions from multiple sources can result in more accurate predictions. Finally, it is shown that further improvements in prediction accuracy can be gained with the use of biologically inspired post-processing of predictions.

Algorithms↗
PubMedDate not supplied

Computer-assisted bone age assessment based on features automatically extracted from a hand radiograph.

This paper presents a computer-aided classification algorithm to assist the radiologist in the bone age assessment of pediatric patients. The classification is based on features automatically extracted from two regions of Computed Radiography (CR) left hand wrist images: phalangeal region of interest (PROI) and carpal bone region of interest (CROI). Due to imprecise nature of the bone age assessment problem, a fuzzy classifier for both regions has been developed. After defining a membership function for each region, features are processed yielding a matrix which maps the set of features to a year of age within the predefined range. The grades of membership are described as membership function values in the interval [0, 1]. A classification rule based on a max-sum operator, processes the matrix assessing the bone age. Since both regions are analyzed independently, two bone age assessments are obtained. They reflect the phalangeal and carpal bones maturity individually. In pathological cases the discrepancy between both assessments may reach as much as 2 yr.

Age Determination by Skeleton↗
PubMed2001

Application of multivariate statistics to vestibular testing: discriminating between Menière's disease and migraine associated dizziness.

Menière's disease (MD) and migraine associated dizziness (MAD) are two disorders that can have similar symptomatologies, but differ vastly in treatment. Vestibular testing is sometimes used to help differentiate between these disorders, but the inefficiency of a human interpreter analyzing a multitude of variables independently decreases its utility. Our hypothesis was that we could objectively discriminate between patients with MD and those with MAD using select variables from the vestibular test battery. Sinusoidal harmonic acceleration test variables were reduced to three vestibulo-ocular reflex physiologic parameters: gain, time constant, and asymmetry. A combination of these parameters plus a measurement of reduced vestibular response from caloric testing allowed us to achieve a joint classification rate of 91%, independent quadratic classification algorithm. Data from posturography were not useful for this type of differentiation. Overall, our classification function can be used as an unbiased assistant to discriminate between MD and MAD and gave us insight into the pathophysiologic differences between the two disorders.

Adolescent↗